public Model(MeasureList measures, bool outcomeIsLogNormallyDistributed, McmcParameters mcmcParams)
{
OelStdz = new OelStandardizer(this);
Measures = measures;
this.ClassName = this.GetType().Name;
if (mcmcParams == null)
{
mcmcParams = new McmcParameters(); // default values
this.Messages.AddWarning("Mcmc parameters were undefined, using default values", this.ClassName);
}
this.Messages.Add(measures.Error);
this.Messages.Add(mcmcParams.Error);
this.NIter = mcmcParams.NIter;
this.NBurnin = mcmcParams.NBurnin;
this.NThin = mcmcParams.NThin;
this.MonitorBurnin = mcmcParams.MonitorBurnin;
this.OutcomeIsLogNormallyDistributed = outcomeIsLogNormallyDistributed;
if (this.OutcomeIsLogNormallyDistributed)
{
OelStdz.StandardizeObservations();
}
this.Data = new DataSummary(measures, this.OutcomeIsLogNormallyDistributed);
this.ME = measures.ME;
this.OEL = measures.OEL;
}
public SEGUninformativeModel(MeasureList measures, UninformativeModelParameters specificParams, McmcParameters mcmcParams = null)
: base(measures, specificParams.LogNormalDstrn, /*new Range(specificParams.MuLower, specificParams.MuUpper, specificParams.InitMu),*/ mcmcParams)
{
this.MuLower = specificParams.MuLower;
this.MuUpper = specificParams.MuUpper;
this.SDRange = specificParams.SDRange;
this.InitMu = specificParams.InitMu;
this.InitSD = specificParams.InitSD;
this.Result = new ModelResult(this, "mu", "sd");
bool testSD = double.IsNaN(this.InitSD) || (this.InitSD == 0);
if (Tools.IsND(this.InitMu) || testSD)
{
InitialValues initVals = WebExpoFunctions3.DefaultInits(this.Data, this.OutcomeIsLogNormallyDistributed, Tools.Combine(this.MuLower, this.MuUpper), this.SDRange, includeCensoredData: false);
if (Tools.IsND(this.InitMu))
{
this.InitMu = initVals.Mu;
}
if (testSD)
{
this.InitSD = initVals.SigmaWithin;
}
}
if (this.ME.ThroughCV)
{
this.Result.Chains.Add("cv");
}
}// end constructor
public virtual string ToString(MeasureList.FieldSeparator fs)
{
string fieldSeparator = MeasureList.GetFieldSeparator(fs);
return(string.Format(CultureInfo.InvariantCulture, "{0}{2}{1}",
A,
Worker == null ? "" : Worker.Tag,
fieldSeparator));
}
public override string ToString(MeasureList.FieldSeparator fs)
{
string fieldSeparator = MeasureList.GetFieldSeparator(fs);
return(string.Format(CultureInfo.InvariantCulture, "[{0},{1}]{3}{2}",
A,
B,
Worker == null ? "" : Worker.Tag,
fieldSeparator));
}
public SEGInformedVarModel(MeasureList measures, SEGInformedVarModelParameters specificParams, McmcParameters mcmcParams = null, PastDataSummary pastDataSummary = null)
: base(measures, specificParams.LogNormalDstrn, mcmcParams)
{
this.PastData = pastDataSummary == null ? PastDataSummary.EmptyObject : pastDataSummary;
this.Messages.Add(this.PastData.Messages);
this.LogSigmaMu = specificParams.LogSigmaMu;
this.LogSigmaPrec = specificParams.LogSigmaPrec;
this.InitSigma = specificParams.InitSigma;
this.MuLower = specificParams.MuLower;
this.MuUpper = specificParams.MuUpper;
this.InitMu = specificParams.InitMu;
this.Result = new ModelResult(this, "mu", "sd");
if (this.ME.ThroughCV)
{
this.Result.Chains.Add("cv");
}
}// end constructor
internal DataSummary(MeasureList ml, bool logNormalDistrn)
{
this.MeasureList = ml;
this.UncensoredMeasures = MeasureList.measuresByCensoringType[Measure.MeasureType.Uncensored].ToArray();
this.LTMeasures = MeasureList.measuresByCensoringType[Measure.MeasureType.LessThan].ToArray();
this.GTMeasures = MeasureList.measuresByCensoringType[Measure.MeasureType.GreaterThan].ToArray();
this.IntervalMeasures = MeasureList.measuresByCensoringType[Measure.MeasureType.Interval].ToArray();
this.logNormalDistrn = logNormalDistrn;
this.N = ml.N;
this.MEAny = ml.MEAny;
this.METhroughCV = ml.METhroughCV;
this.METhroughSD = ml.METhroughSD;
this.raw = new RawData();
this.raw.Y = ml.measuresByCensoringType[Measure.MeasureType.Uncensored].Select(x => x.A).ToArray();
this.raw.UncensoredSum = this.raw.Y.Sum();
this.raw.UncensoredSum2 = this.raw.Y.Sqr().Sum();
this.raw.LT = ml.measuresByCensoringType[Measure.MeasureType.LessThan].Select(x => x.A).ToArray();
this.raw.GT = ml.measuresByCensoringType[Measure.MeasureType.GreaterThan].Select(x => x.A).ToArray();
this.raw.IntervalCensored = Tuple.Create(
ml.measuresByCensoringType[Measure.MeasureType.Interval].Select(x => x.A).ToArray(),
ml.measuresByCensoringType[Measure.MeasureType.Interval].Select(x => x.B).ToArray());
this.AnyGT = GTLength > 0;
this.AnyLT = LTLength > 0;
this.AnyIntervalCensored = IntervalLength > 0;
this.AnyCensored = this.AnyGT || this.AnyLT || this.AnyIntervalCensored;
if (ml.ME.ThroughCV || logNormalDistrn)
{
Func <double, bool> test;
if (logNormalDistrn)
{
test = delegate(double x)
{
return(x <= 0);
};
}
else
{
test = delegate(double x)
{
return(x < 0);
};
}
string firstErrSrc = "";
while (true)
{
if (this.raw.Y.Any(xx => test(xx)))
{
firstErrSrc = "uncensored measure";
break;
}
if (this.raw.GT.Any(xx => test(xx)))
{
firstErrSrc = "'greater than' measure";
break;
}
if (this.raw.LT.Any(xx => test(xx)))
{
firstErrSrc = "'less than' measure";
break;
}
if (this.raw.IntervalCensored.Item1.Any(xx => test(xx)))
{
firstErrSrc = "'interval' measure";
break;
}
break;
}
if (firstErrSrc != string.Empty)
{
//TODO: Il faudra vérifier si cette exception peut ou non se produire.
string fmt = "{1} and negative data points (as found in {0}) are irreconciliable.";
firstErrSrc = string.Format(
fmt,
firstErrSrc,
logNormalDistrn ? "A log-normally distributed outcome" : "Measurement Error specified through a Coefficient of Variation");
throw new WEException(firstErrSrc);
}
}
if (logNormalDistrn)
{
this.logOfRaw = new RawData();
this.logOfRaw.Y = this.raw.Y.Log();
this.logOfRaw.UncensoredSum = this.logOfRaw.Y.Sum();
this.logOfRaw.UncensoredSum2 = this.logOfRaw.Y.Sqr().Sum();
this.logOfRaw.GT = this.raw.GT.Log();
this.logOfRaw.LT = this.raw.LT.Log();
this.logOfRaw.IntervalCensored = Tuple.Create(
this.raw.IntervalCensored.Item1.Log(),
this.raw.IntervalCensored.Item2.Log());
}
this.WorkersByTag = MeasureList.WorkersByTag;
for (int iw = 0; iw < this.WorkersByTag.Values.Count; iw++)
{
this.WorkersByTag.Values[iw].Ordinal = iw;
}
this.WorkerCounts = new int[this.MeasuresByWorker.Keys.Count];
foreach (KeyValuePair <Worker, List <Measure> > kv in this.MeasuresByWorker)
{
this.WorkerCounts[kv.Key.Ordinal] = kv.Value.Count;
}
this.WorkersByOrdinal = this.WorkersByTag.Values.ToArray();
}
public BetweenWorkerModel(MeasureList measures, AbstractBWModelParameters specificParams, McmcParameters mcmcParams = null)
: base(measures, specificParams.LogNormalDstrn, mcmcParams)
{
this.Result = new ModelResult(this, "muOverall", "sigmaWithin", "sigmaBetween");
if (!measures.IsWorkerInfoComplete)
{
this.Messages.AddError("Incomplete worker information.", this.ClassName);
}
if (this.Data.MEAny)
{
if (this.Data.METhroughSD && !MeasurementErrorSupport.MESD)
{
this.Messages.AddError("No support for METhrougSD.", this.ClassName);
}
else if (this.Data.METhroughCV && !MeasurementErrorSupport.me_CV)
{
this.Messages.AddError("No support for METhrougCV.", this.ClassName);
}
}
if (this.Messages.Level == Message.Severity.Error)
{
return;
}
this.UseUniformPriorOnSds = specificParams.UseUniformPriorOnSds;
if (this.UseUniformPriorOnSds)
{
this.SigmaBetweenRange = Tools.Copy(((BWModelParameters_UniformPriorOnSDs)specificParams).SigmaBetweenRange);
this.SigmaWithinRange = ((BWModelParameters_UniformPriorOnSDs)specificParams).SigmaWithinRange;
}
else
{
this.LogSigmaBetweenMu = ((BWModelParameters)specificParams).LogSigmaBetweenMu;
this.LogSigmaBetweenPrec = ((BWModelParameters)specificParams).LogSigmaBetweenPrec;
this.LogSigmaWithinMu = ((BWModelParameters)specificParams).LogSigmaWithinMu;
this.LogSigmaWithinPrec = ((BWModelParameters)specificParams).LogSigmaWithinPrec;
}
//4 paramètres communs aux 2 formes que prend le modèle.
this.MuOverallLower = specificParams.MuOverallLower;
this.MuOverallUpper = specificParams.MuOverallUpper;
this.InitMuOverall = specificParams.InitMuOverall;
this.InitSigmaWithin = specificParams.InitSigmaWithin;
this.MuOverallRange = Tools.Combine(this.MuOverallLower, this.MuOverallUpper);
this.Result.AddWorkerMuChains(Data.WorkersByTag.Values);
if (!Data.AnyCensored && UseUniformPriorOnSds)
{
//
//# If there is no variation observed within subjects,
//# then we require a non-null lower bound for sigma.within
//
if (SigmaWithinRange[0] == 0)
{
bool problem = (Data.NWorkers == Data.N); //il devrait donc y avoir plus d'une mesure pour au moins un travailleur
if (!problem)
{
problem = true;
foreach (KeyValuePair <Worker, List <Measure> > kv in Data.MeasuresByWorker)
{
if (kv.Value.Count <= 1)
{
continue;
}
//at least two measures
double vari = kv.Value.Select(x => x.A).Variance();
if (double.IsNaN(vari) || (vari == 0))
{
continue;
}
else
{
problem = false;
break;
}
} //foreach
}
if (problem)
{
this.Messages.AddError("Lower bound for SigmaWithinRange must be > 0 due to observed null within-subjects variance.", this.ClassName);
return;
}
}
}
if (specificParams.GetType() == typeof(BWModelParameters))// && (Tools.IsND(this.InitMuOverall) || Tools.IsND(this.InitSigmaWithin)))
{
InitialValues initValues = specificParams.DefaultInits(this.Data, includeCensoredData: false);
if (Tools.IsND(this.InitMuOverall))
{
this.InitMuOverall = initValues.Mu;
}
if (Tools.IsND(this.InitSigmaWithin))
{
this.InitSigmaWithin = initValues.SigmaWithin;
}
this.NormalizedY = initValues.NormalizedY.ToArray();
}
}